Image Inpainting

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

12 leaderboard tables shown for this task, 12 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted. 10 shown of 12 until expanded.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

17 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

3 subtasks in the archive's task tree.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

30 shown of 331 papers with code (708 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Image Inpainting for Irregular Holes Using Partial Convolutions
  20 Apr 2018 60 repositories listed Syntology ran 9 of 31 samples · 22 unverified · 3 pointer-only (licence)
  Existing deep learning based image inpainting methods use a standard convolutional network over the corrupted image, using convolutional filter responses conditioned on both valid pixels as well as the substitute values…
• High-Resolution Image Synthesis with Latent Diffusion Models
  20 Dec 2021 41 repositories listed Syntology ran 19 of 28 samples · 9 unverified · 5 pointer-only (licence)
  By decomposing the image formation process into a sequential application of denoising autoencoders, diffusion models (DMs) achieve state-of-the-art synthesis results on image data and beyond.
• Free-Form Image Inpainting with Gated Convolution
  10 Jun 2018 30 repositories listed Syntology ran 1 of 7 samples · 6 unverified
  We present a generative image inpainting system to complete images with free-form mask and guidance.
• Generative Image Inpainting with Contextual Attention
  24 Jan 2018 28 repositories listed
  Motivated by these observations, we propose a new deep generative model-based approach which can not only synthesize novel image structures but also explicitly utilize surrounding image features as references during…
• Implicit Neural Representations with Periodic Activation Functions
  17 Jun 2020 25 repositories listed Syntology ran 49 of 71 samples · 22 unverified · 8 pointer-only (licence)
  However, current network architectures for such implicit neural representations are incapable of modeling signals with fine detail, and fail to represent a signal's spatial and temporal derivatives, despite the fact…
• EdgeConnect: Generative Image Inpainting with Adversarial Edge Learning
  1 Jan 2019 20 repositories listed Syntology ran 4 of 4 samples · 0 unverified · 4 pointer-only (licence)
  The edge generator hallucinates edges of the missing region (both regular and irregular) of the image, and the image completion network fills in the missing regions using hallucinated edges as a priori.
• Consistency Models
  2 Mar 2023 15 repositories listed Syntology ran 28 of 57 samples · 29 unverified · 8 pointer-only (licence)
  Through extensive experiments, we demonstrate that they outperform existing distillation techniques for diffusion models in one- and few-step sampling, achieving the new state-of-the-art FID of 3.
• Score-Based Generative Modeling through Stochastic Differential Equations
  26 Nov 2020 15 repositories listed Syntology ran 15 of 23 samples · 8 unverified · 4 pointer-only (licence)
  Combined with multiple architectural improvements, we achieve record-breaking performance for unconditional image generation on CIFAR-10 with an Inception score of 9.
• Deep Image Prior
  29 Nov 2017 14 repositories listed Syntology ran 5 of 6 samples · 1 unverified · 6 pointer-only (licence)
  In this paper, we show that, on the contrary, the structure of a generator network is sufficient to capture a great deal of low-level image statistics prior to any learning.
• Generative Modeling by Estimating Gradients of the Data Distribution
  12 Jul 2019 13 repositories listed Syntology ran 14 of 22 samples · 8 unverified · 9 pointer-only (licence)
  We introduce a new generative model where samples are produced via Langevin dynamics using gradients of the data distribution estimated with score matching.
• Resolution-robust Large Mask Inpainting with Fourier Convolutions
  15 Sep 2021 8 repositories listed Syntology ran 0 of 4 samples · 4 unverified
  We find that one of the main reasons for that is the lack of an effective receptive field in both the inpainting network and the loss function.
• Semantic Image Inpainting with Deep Generative Models
  26 Jul 2016 7 repositories listed Syntology ran 1 of 13 samples · 12 unverified · 3 pointer-only (licence)
  In this paper, we propose a novel method for semantic image inpainting, which generates the missing content by conditioning on the available data.
• Contextual Residual Aggregation for Ultra High-Resolution Image Inpainting
  19 May 2020 6 repositories listed Syntology ran 2 of 9 samples · 7 unverified
  Since convolutional layers of the neural network only need to operate on low-resolution inputs and outputs, the cost of memory and computing power is thus well suppressed.
• Deep Fusion Network for Image Completion
  17 Apr 2019 5 repositories listed
  The fusion block not only provides a smooth fusion between restored and existing content, but also provides an attention map to make network focus more on the unknown pixels.
• Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model
  1 Dec 2022 4 repositories listed Syntology ran 12 of 23 samples · 11 unverified
  Most existing Image Restoration (IR) models are task-specific, which can not be generalized to different degradation operators.
• Image Inpainting via Conditional Texture and Structure Dual Generation
  22 Aug 2021 4 repositories listed Syntology ran 0 of 5 samples · 5 unverified
  Deep generative approaches have recently made considerable progress in image inpainting by introducing structure priors.
• High-Fidelity Pluralistic Image Completion with Transformers
  25 Mar 2021 4 repositories listed Syntology ran 7 of 8 samples · 1 unverified · 8 pointer-only (licence)
  Image completion has made tremendous progress with convolutional neural networks (CNNs), because of their powerful texture modeling capacity.
• Accelerated MRI with Un-trained Neural Networks
  6 Jul 2020 4 repositories listed
  Convolutional Neural Networks (CNNs) are highly effective for image reconstruction problems.
• Joint learning of variational representations and solvers for inverse problems with partially-observed data
  5 Jun 2020 4 repositories listed
  The variational cost and the gradient-based solver are both stated as neural networks using automatic differentiation for the latter.
• SC-FEGAN: Face Editing Generative Adversarial Network with User's Sketch and Color
  18 Feb 2019 4 repositories listed
  We present a novel image editing system that generates images as the user provides free-form mask, sketch and color as an input.
• LeftRefill: Filling Right Canvas based on Left Reference through Generalized Text-to-Image Diffusion Model
  19 May 2023 3 repositories listed
  As an exemplar, we leverage LeftRefill to address two different challenges: reference-guided inpainting and novel view synthesis, based on the pre-trained StableDiffusion.
• Generative Modeling in Structural-Hankel Domain for Color Image Inpainting
  25 Nov 2022 3 repositories listed
  To better apply the score-based generative model to learn the internal statistical distribution within patches, the large-scale Hankel matrices are finally folded into the higher dimensional tensors for prior learning.
• Feature Refinement to Improve High Resolution Image Inpainting
  27 Jun 2022 3 repositories listed
  In this paper, we address the problem of degradation in inpainting quality of neural networks operating at high resolutions.
• Planning with Diffusion for Flexible Behavior Synthesis
  20 May 2022 3 repositories listed
  Model-based reinforcement learning methods often use learning only for the purpose of estimating an approximate dynamics model, offloading the rest of the decision-making work to classical trajectory optimizers.
• RePaint: Inpainting using Denoising Diffusion Probabilistic Models
  24 Jan 2022 3 repositories listed Syntology ran 1 of 3 samples · 2 unverified · 3 pointer-only (licence)
  In this work, we propose RePaint: A Denoising Diffusion Probabilistic Model (DDPM) based inpainting approach that is applicable to even extreme masks.
• Image Inpainting with Edge-guided Learnable Bidirectional Attention Maps
  25 Apr 2021 3 repositories listed
  In this paper, we present an edge-guided learnable bidirectional attention map (Edge-LBAM) for improving image inpainting of irregular holes with several distinct merits.
• AIM 2020 Challenge on Image Extreme Inpainting
  2 Oct 2020 3 repositories listed
  This report focuses on proposed solutions and results for two different tracks on extreme image inpainting: classical image inpainting and semantically guided image inpainting.
• Image Fine-grained Inpainting
  7 Feb 2020 3 repositories listed
  Besides, we devise a geometrical alignment constraint item to compensate for the pixel-based distance between prediction features and ground-truth ones.
• Image2StyleGAN++: How to Edit the Embedded Images?
  26 Nov 2019 3 repositories listed Syntology ran 2 of 2 samples · 0 unverified · 2 pointer-only (licence)
  We propose Image2StyleGAN++, a flexible image editing framework with many applications.
• Indoor Depth Completion with Boundary Consistency and Self-Attention
  22 Aug 2019 3 repositories listed Syntology ran 0 of 3 samples · 3 unverified
  We utilize self-attention mechanism, previously used in image inpainting fields, to extract more useful information in each layer of convolution so that the complete depth map is enhanced.

Syntology lines on 18 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.